AD model-pyramid
Right-size MODEL + EFFORT for the session and for each subagent at fan-out time, and decide whether to attach an advisor. Two axes: capability gap → change model; thoroughness gap → change effort. Use when spawning / fanning out / delegating subagents, or when asked which model or effort something should get: "$model-pyramid". NOT API price shopping.
Right-size MODEL + EFFORT for the session and for each subagent at fan-out time, and decide whether to attach an advisor.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
medium Concealment
en-hide-from-userscripts/check_plan.mjs:93Instruction to hide actions from the user (quoted — discussed, not commanded)add("warning", "effort-falls-back", where, `${model} does not support "${effort}" — it will silently run as "${fallback}"`);quoted -
low Risky intent
intent-offensive-securityreferences/orchestration.md:71Offensive-security / dual-use content (legitimate for authorised testing; review intended use)judge, a fresh-context red team): those defend against correlated error, not against
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1586 tokens
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 352: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.